wiki_o_30

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.3683

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 256
  • eval_batch_size: 256
  • seed: 30
  • optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
6.9714 1.0 399 5.9843
5.6132 2.0 798 5.3491
5.159 3.0 1197 5.0553
4.8974 4.0 1596 4.8676
4.7058 5.0 1995 4.7338
4.5523 6.0 2394 4.6314
4.4235 7.0 2793 4.5561
4.3123 8.0 3192 4.5001
4.2136 9.0 3591 4.4575
4.127 10.0 3990 4.4262
4.0503 11.0 4389 4.4051
3.9816 12.0 4788 4.3878
3.92 13.0 5187 4.3770
3.8651 14.0 5586 4.3691
3.8158 15.0 5985 4.3645
3.7721 16.0 6384 4.3642
3.7336 17.0 6783 4.3644
3.7006 18.0 7182 4.3670
3.6733 19.0 7581 4.3664
3.6526 20.0 7980 4.3683

Framework versions

  • Transformers 4.56.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.0
Downloads last month
2
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support